The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Improving Neural Architecture Search by Minimizing Worst-Case Validation Loss
- Published
- Record updated
Summary
This paper addresses neural architecture search (NAS), which automatically finds high-performance network architectures. Existing NAS methods minimize average-case validation loss, so the architectures they find predict poorly in worst-case scenarios. The authors propose a multilevel optimization framework that uses a deep generative model to create adversarial validation examples and minimizes the loss on them, and report that experiments on a variety of datasets demonstrate its effectiveness.